InstantID

What is InstantID AI

InstantID is a new state-of-the-art tuning-free method to achieve ID-Preserving generation with only single image, supporting various downstream tasks.

There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and the need for multiple reference images. Conversely, existing ID embedding-based methods, while requiring only a single forward inference, face challenges: they either necessitate extensive fine-tuning across numerous model parameters, lack compatibility with community pre-trained models, or fail to maintain high face fidelity. Addressing these limitations, we introduce InstantID, a powerful diffusion model-based solution. Our plug-and-play module adeptly handles image personalization in various styles using just a single facial image, while ensuring high fidelity. To achieve this, we design a novel IdentityNet by imposing strong semantic and weak spatial conditions, integrating facial and landmark images with textual prompts to steer the image generation. InstantID demonstrates exceptional performance and efficiency, proving highly beneficial in real-world applications where identity preservation is paramount. Moreover, our work seamlessly integrates with popular pre-trained text-to-image diffusion models like SD1.5 and SDXL, serving as an adaptable plugin. Our codes and pre-trained checkpoints will be available at this URL.

We are different from previous works in the following aspects:

(1) We do not train UNet, so we can preserve the generation ability of the original text-to-image model and be compatible with existing pre-trained models and ControlNets in the community;

(2) We don’t require test-time tuning, so for a specific character, there is no need to collect multiple images for fine-tuning, only a single image needs to be inferred once;

(3) We achieve better face fidelity, and retain the editability of text.

InstantID AI supports both Stylizated and Realistic styles.

How to use:

1. Upload a person image. For multiple person images, we will only detect the biggest face. Make sure face is not too small and not significantly blocked or blurred.
2. (Optionally) upload another person image as reference pose. If not uploaded, we will use the first person image to extract landmarks. If you use a cropped face at step1, it is recommeneded to upload it to extract a new pose.
3. Enter a text prompt as done in normal text-to-image models.
4. Click the Submit button to start customizing.
5. Share your customizd photo with your friends, enjoy?!

Usage tips of InstantID

1. If you’re unsatisfied with the similarity, increase the weight of controlnet_conditioning_scale (IdentityNet) and ip_adapter_scale (Adapter).
2. If the generated image is over-saturated, decrease the ip_adapter_scale. If not work, decrease controlnet_conditioning_scale.
3. If text control is not as expected, decrease ip_adapter_scale.
4. Find a good base model always makes a difference.

Comparison with Previous Works

Comparison with existing tuning-free state-of-the-art techniques. InstantID achieves better fidelity and retain good text editability (faces and styles blend better).

Comparison with pre-trained character LoRAs. We don’t need multiple images and still can achieve competitive results as LoRAs without any training.

Comparison with InsightFace Swapper (also known as ROOP or Refactor). However, in non-realistic style, our work is more flexible on the integration of face and background.